Skip to content

Instantly share code, notes, and snippets.

@altbridgetech

altbridgetech/TensorRT_mnist.ipynb Secret

Last active January 2, 2022 08:41
Show Gist options
  • Save altbridgetech/c2a00c0d7a8416885ee1a064d3c77d6e to your computer and use it in GitHub Desktop.
Save altbridgetech/c2a00c0d7a8416885ee1a064d3c77d6e to your computer and use it in GitHub Desktop.
Download ZIP
TensorRT-tar-installation
Display the source blob
Display the rendered blob
Raw
TensorRT_mnist.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"accelerator": "GPU",
"colab": {
"name": "TensorRT-mnist.ipynb のコピー",
"provenance": [],
"collapsed_sections": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
}
},
"cells": [
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "RtLo0sRUBfiP",
"outputId": "b09c82e9-1fff-4208-b370-8f6a8a75c5d4"
},
"source": [
"from google.colab import drive\n",
"drive.mount('/content/drive')"
],
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"text": [
"Mounted at /content/drive\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "GPA7v2LStv-u",
"outputId": "4f4e4221-45c2-4c40-b276-00d3c9c116f3"
},
"source": [
"!nvidia-smi"
],
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"text": [
"Mon Jul 12 08:45:53 2021 \n",
"+-----------------------------------------------------------------------------+\n",
"| NVIDIA-SMI 470.42.01 Driver Version: 460.32.03 CUDA Version: 11.2 |\n",
"|-------------------------------+----------------------+----------------------+\n",
"| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |\n",
"| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |\n",
"| | | MIG M. |\n",
"|===============================+======================+======================|\n",
"| 0 Tesla K80 Off | 00000000:00:04.0 Off | 0 |\n",
"| N/A 31C P8 30W / 149W | 0MiB / 11441MiB | 0% Default |\n",
"| | | N/A |\n",
"+-------------------------------+----------------------+----------------------+\n",
" \n",
"+-----------------------------------------------------------------------------+\n",
"| Processes: |\n",
"| GPU GI CI PID Type Process name GPU Memory |\n",
"| ID ID Usage |\n",
"|=============================================================================|\n",
"| No running processes found |\n",
"+-----------------------------------------------------------------------------+\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "6giQEmtzIDUi",
"outputId": "01cc5a76-4e91-49c1-aa69-8b2bf1454505"
},
"source": [
"!cat /etc/issue\n",
"!nvcc -V\n",
"!python -V\n",
"!dpkg -l | grep \"cudnn\""
],
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"text": [
"Ubuntu 18.04.5 LTS \\n \\l\n",
"\n",
"nvcc: NVIDIA (R) Cuda compiler driver\n",
"Copyright (c) 2005-2020 NVIDIA Corporation\n",
"Built on Wed_Jul_22_19:09:09_PDT_2020\n",
"Cuda compilation tools, release 11.0, V11.0.221\n",
"Build cuda_11.0_bu.TC445_37.28845127_0\n",
"Python 3.7.10\n",
"ii libcudnn7 7.6.5.32-1+cuda10.1 amd64 cuDNN runtime libraries\n",
"ii libcudnn7-dev 7.6.5.32-1+cuda10.1 amd64 cuDNN development libraries and headers\n",
"hi libcudnn8 8.0.4.30-1+cuda11.0 amd64 cuDNN runtime libraries\n",
"ii libcudnn8-dev 8.0.4.30-1+cuda11.0 amd64 cuDNN development libraries and headers\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "_mf7jAur3GgO"
},
"source": [
"!tar -zxf /content/drive/MyDrive/TensorRT/TensorRT-7.2.2.3.Ubuntu-18.04.x86_64-gnu.cuda-11.0.cudnn8.0.tar.gz"
],
"execution_count": 5,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "tJMSqBCSrnYB",
"outputId": "de7096ca-b792-4435-eddb-255e864b9cde"
},
"source": [
"%cd /content/TensorRT-7.2.2.3/python\n",
"!sudo pip3 install tensorrt-7.2.2.3-cp37-none-linux_x86_64.whl"
],
"execution_count": 6,
"outputs": [
{
"output_type": "stream",
"text": [
"/content/TensorRT-7.2.2.3/python\n",
"Processing ./tensorrt-7.2.2.3-cp37-none-linux_x86_64.whl\n",
"Installing collected packages: tensorrt\n",
"Successfully installed tensorrt-7.2.2.3\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "vdARGeubrEeO",
"outputId": "417929ea-7a3a-4f10-8dd8-090bf72a9800"
},
"source": [
"%cd /content/TensorRT-7.2.2.3/uff\n",
"!sudo pip3 install uff-0.6.9-py2.py3-none-any.whl"
],
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"text": [
"/content/TensorRT-7.2.2.3/uff\n",
"Processing ./uff-0.6.9-py2.py3-none-any.whl\n",
"Requirement already satisfied: numpy>=1.11.0 in /usr/local/lib/python3.7/dist-packages (from uff==0.6.9) (1.19.5)\n",
"Requirement already satisfied: protobuf>=3.3.0 in /usr/local/lib/python3.7/dist-packages (from uff==0.6.9) (3.17.3)\n",
"Requirement already satisfied: six>=1.9 in /usr/local/lib/python3.7/dist-packages (from protobuf>=3.3.0->uff==0.6.9) (1.15.0)\n",
"Installing collected packages: uff\n",
"Successfully installed uff-0.6.9\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "SCo2T3TtrULp",
"outputId": "2020fc44-d335-4163-be97-0750fe74efd5"
},
"source": [
"%cd /content/TensorRT-7.2.2.3/graphsurgeon/\n",
"!sudo pip3 install graphsurgeon-0.4.5-py2.py3-none-any.whl"
],
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"text": [
"/content/TensorRT-7.2.2.3/graphsurgeon\n",
"Processing ./graphsurgeon-0.4.5-py2.py3-none-any.whl\n",
"Installing collected packages: graphsurgeon\n",
"Successfully installed graphsurgeon-0.4.5\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "YxfAXY8QrikE",
"outputId": "8ece264f-8720-4c07-a70b-6ef1d154b71c"
},
"source": [
"%cd /content/TensorRT-7.2.2.3/onnx_graphsurgeon/\n",
"!sudo pip3 install onnx_graphsurgeon-0.2.6-py2.py3-none-any.whl"
],
"execution_count": 9,
"outputs": [
{
"output_type": "stream",
"text": [
"/content/TensorRT-7.2.2.3/onnx_graphsurgeon\n",
"Processing ./onnx_graphsurgeon-0.2.6-py2.py3-none-any.whl\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.7/dist-packages (from onnx-graphsurgeon==0.2.6) (1.19.5)\n",
"Collecting onnx\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/3f/9b/54c950d3256e27f970a83cd0504efb183a24312702deed0179453316dbd0/onnx-1.9.0-cp37-cp37m-manylinux2010_x86_64.whl (12.2MB)\n",
"\u001b[K |████████████████████████████████| 12.2MB 180kB/s \n",
"\u001b[?25hRequirement already satisfied: protobuf in /usr/local/lib/python3.7/dist-packages (from onnx->onnx-graphsurgeon==0.2.6) (3.17.3)\n",
"Requirement already satisfied: six in /usr/local/lib/python3.7/dist-packages (from onnx->onnx-graphsurgeon==0.2.6) (1.15.0)\n",
"Requirement already satisfied: typing-extensions>=3.6.2.1 in /usr/local/lib/python3.7/dist-packages (from onnx->onnx-graphsurgeon==0.2.6) (3.7.4.3)\n",
"Installing collected packages: onnx, onnx-graphsurgeon\n",
"Successfully installed onnx-1.9.0 onnx-graphsurgeon-0.2.6\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "vLMYK4W6rt_e",
"outputId": "ef5eb702-ff89-4cde-c322-893839e71f7c"
},
"source": [
"%cd /content/TensorRT-7.2.2.3/samples/python/network_api_pytorch_mnist/\n",
"!python3 -m pip install -r requirements.txt"
],
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"text": [
"/content/TensorRT-7.2.2.3/samples/python/network_api_pytorch_mnist\n",
"Ignoring torch: markers 'python_version == \"2.7\" and platform_machine == \"x86_64\" and sys_platform == \"linux2\"' don't match your environment\n",
"Ignoring torchvision: markers 'python_version == \"2.7\" and platform_machine == \"x86_64\" and sys_platform == \"linux2\"' don't match your environment\n",
"Looking in links: https://download.pytorch.org/whl/torch_stable.html\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.7/dist-packages (from -r requirements.txt (line 1)) (1.19.5)\n",
"Collecting torch==1.5.0+cpu\n",
"\u001b[?25l Downloading https://download.pytorch.org/whl/cpu/torch-1.5.0%2Bcpu-cp37-cp37m-linux_x86_64.whl (127.3MB)\n",
"\u001b[K |████████████████████████████████| 127.3MB 45kB/s \n",
"\u001b[?25hCollecting torchvision==0.6.0\n",
"\u001b[?25l Downloading https://download.pytorch.org/whl/cu92/torchvision-0.6.0%2Bcu92-cp37-cp37m-linux_x86_64.whl (6.5MB)\n",
"\u001b[K |████████████████████████████████| 6.5MB 3.2MB/s \n",
"\u001b[?25hCollecting Pillow==6.2.2\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/c3/3f/03375124676ab49ca6e6917c0f1f663afb8354d5d24e12f4fe4587a39ae2/Pillow-6.2.2-cp37-cp37m-manylinux1_x86_64.whl (2.1MB)\n",
"\u001b[K |████████████████████████████████| 2.1MB 5.2MB/s \n",
"\u001b[?25hCollecting pycuda\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/5a/56/4682a5118a234d15aa1c8768a528aac4858c7b04d2674e18d586d3dfda04/pycuda-2021.1.tar.gz (1.7MB)\n",
"\u001b[K |████████████████████████████████| 1.7MB 17.8MB/s \n",
"\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
" Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
" Preparing wheel metadata ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: future in /usr/local/lib/python3.7/dist-packages (from torch==1.5.0+cpu->-r requirements.txt (line 3)) (0.16.0)\n",
"Requirement already satisfied: appdirs>=1.4.0 in /usr/local/lib/python3.7/dist-packages (from pycuda->-r requirements.txt (line 8)) (1.4.4)\n",
"Collecting pytools>=2011.2\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/52/26/c7ab098ceb4e4e3f0e66e21257a286bb455ea22af7afefbd704d9ccf324c/pytools-2021.2.7.tar.gz (63kB)\n",
"\u001b[K |████████████████████████████████| 71kB 7.8MB/s \n",
"\u001b[?25hCollecting mako\n",
"\u001b[?25l Downloading https://files.pythonhosted.org/packages/f3/54/dbc07fbb20865d3b78fdb7cf7fa713e2cba4f87f71100074ef2dc9f9d1f7/Mako-1.1.4-py2.py3-none-any.whl (75kB)\n",
"\u001b[K |████████████████████████████████| 81kB 7.8MB/s \n",
"\u001b[?25hRequirement already satisfied: MarkupSafe>=0.9.2 in /usr/local/lib/python3.7/dist-packages (from mako->pycuda->-r requirements.txt (line 8)) (2.0.1)\n",
"Building wheels for collected packages: pycuda\n",
" Building wheel for pycuda (PEP 517) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for pycuda: filename=pycuda-2021.1-cp37-cp37m-linux_x86_64.whl size=627098 sha256=38207ebe5391c765b40b4683fb283d7d8461a097d18acf8ff3f8d5e15bbde6a1\n",
" Stored in directory: /root/.cache/pip/wheels/d5/55/64/fd4dddcc5f1c25eebd90b5291c3769101dc978c70165685512\n",
"Successfully built pycuda\n",
"Building wheels for collected packages: pytools\n",
" Building wheel for pytools (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for pytools: filename=pytools-2021.2.7-py2.py3-none-any.whl size=60644 sha256=df967e88659110443297bd6be6dceffa4a4ed4cd1bef17ddb7f030247e0d281a\n",
" Stored in directory: /root/.cache/pip/wheels/a0/b5/e5/e65d25997fd77729b9aa214645add18688483e48bbcbab6ffc\n",
"Successfully built pytools\n",
"\u001b[31mERROR: torchtext 0.10.0 has requirement torch==1.9.0, but you'll have torch 1.5.0+cpu which is incompatible.\u001b[0m\n",
"\u001b[31mERROR: bokeh 2.3.2 has requirement pillow>=7.1.0, but you'll have pillow 6.2.2 which is incompatible.\u001b[0m\n",
"\u001b[31mERROR: albumentations 0.1.12 has requirement imgaug<0.2.7,>=0.2.5, but you'll have imgaug 0.2.9 which is incompatible.\u001b[0m\n",
"Installing collected packages: torch, Pillow, torchvision, pytools, mako, pycuda\n",
" Found existing installation: torch 1.9.0+cu102\n",
" Uninstalling torch-1.9.0+cu102:\n",
" Successfully uninstalled torch-1.9.0+cu102\n",
" Found existing installation: Pillow 7.1.2\n",
" Uninstalling Pillow-7.1.2:\n",
" Successfully uninstalled Pillow-7.1.2\n",
" Found existing installation: torchvision 0.10.0+cu102\n",
" Uninstalling torchvision-0.10.0+cu102:\n",
" Successfully uninstalled torchvision-0.10.0+cu102\n",
"Successfully installed Pillow-6.2.2 mako-1.1.4 pycuda-2021.1 pytools-2021.2.7 torch-1.5.0+cpu torchvision-0.6.0+cu92\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "b5gMGOkPpNkZ"
},
"source": [
"import os\n",
"os.environ['LD_LIBRARY_PATH']='/content/TensorRT-7.2.2.3/lib'"
],
"execution_count": 11,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "bCG0tzxypTXL",
"outputId": "f9ce1eac-2736-48f9-d305-07b0c1d1ba0f"
},
"source": [
"!echo $LD_LIBRARY_PATH"
],
"execution_count": 12,
"outputs": [
{
"output_type": "stream",
"text": [
"/content/TensorRT-7.2.2.3/lib\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "FoH-Nsr8sBIh",
"outputId": "073cf797-e158-41c6-b733-cf838f734cd0"
},
"source": [
"%cd /content/TensorRT-7.2.2.3/samples/python/network_api_pytorch_mnist/\n",
"!python3 sample.py"
],
"execution_count": 17,
"outputs": [
{
"output_type": "stream",
"text": [
"/content/TensorRT-7.2.2.3/samples/python/network_api_pytorch_mnist\n",
"Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz to /tmp/mnist/data/MNIST/raw/train-images-idx3-ubyte.gz\n",
"9920512it [05:05, 33995.51it/s] Extracting /tmp/mnist/data/MNIST/raw/train-images-idx3-ubyte.gz to /tmp/mnist/data/MNIST/raw\n",
"Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz to /tmp/mnist/data/MNIST/raw/train-labels-idx1-ubyte.gz\n",
"\n",
"0it [00:00, ?it/s]\u001b[A\n",
" 0% 0/28881 [00:00<?, ?it/s]\u001b[A\n",
"32768it [00:00, 53952.32it/s] \n",
"Extracting /tmp/mnist/data/MNIST/raw/train-labels-idx1-ubyte.gz to /tmp/mnist/data/MNIST/raw\n",
"Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz to /tmp/mnist/data/MNIST/raw/t10k-images-idx3-ubyte.gz\n",
"\n",
"0it [00:00, ?it/s]\u001b[A\n",
" 0% 0/1648877 [00:00<?, ?it/s]\u001b[A\n",
" 1% 16384/1648877 [00:00<00:23, 68688.57it/s]\u001b[A\n",
" 1% 24576/1648877 [00:00<00:30, 52642.71it/s]\u001b[A\n",
" 2% 32768/1648877 [00:01<00:35, 45122.53it/s]\u001b[A\n",
" 2% 40960/1648877 [00:01<00:38, 41724.80it/s]\u001b[A\n",
" 3% 49152/1648877 [00:01<00:40, 39150.96it/s]\u001b[A\n",
" 3% 57344/1648877 [00:01<00:42, 37580.40it/s]\u001b[A\n",
" 4% 65536/1648877 [00:02<00:43, 36445.54it/s]\u001b[A\n",
" 4% 73728/1648877 [00:02<00:44, 35523.25it/s]\u001b[A\n",
" 5% 81920/1648877 [00:02<00:44, 35271.36it/s]\u001b[A\n",
" 5% 90112/1648877 [00:02<00:44, 34900.82it/s]\u001b[A\n",
" 6% 98304/1648877 [00:03<00:44, 34637.83it/s]\u001b[A\n",
" 6% 106496/1648877 [00:03<00:44, 34455.01it/s]\u001b[A\n",
" 7% 114688/1648877 [00:03<00:46, 32668.71it/s]\u001b[A\n",
" 7% 122880/1648877 [00:03<00:44, 34514.93it/s]\u001b[A\n",
" 8% 131072/1648877 [00:04<00:42, 35405.33it/s]\u001b[A\n",
" 8% 139264/1648877 [00:04<00:42, 35710.55it/s]\u001b[A\n",
" 9% 147456/1648877 [00:04<00:41, 35957.49it/s]\u001b[A\n",
" 9% 155648/1648877 [00:04<00:41, 36098.81it/s]\u001b[A\n",
" 10% 163840/1648877 [00:04<00:40, 36247.03it/s]\u001b[A\n",
" 10% 172032/1648877 [00:05<00:40, 36284.34it/s]\u001b[A\n",
" 11% 180224/1648877 [00:05<00:40, 36366.03it/s]\u001b[A\n",
" 11% 188416/1648877 [00:05<00:40, 35662.61it/s]\u001b[A\n",
" 12% 196608/1648877 [00:05<00:41, 35175.78it/s]\u001b[A\n",
" 12% 204800/1648877 [00:06<00:41, 34792.05it/s]\u001b[A\n",
" 13% 212992/1648877 [00:06<00:41, 34621.67it/s]\u001b[A\n",
" 13% 221184/1648877 [00:06<00:41, 34397.64it/s]\u001b[A\n",
" 14% 229376/1648877 [00:06<00:41, 34357.79it/s]\u001b[A\n",
" 14% 237568/1648877 [00:07<00:41, 34203.48it/s]\u001b[A\n",
" 15% 245760/1648877 [00:07<00:40, 34227.81it/s]\u001b[A\n",
" 15% 253952/1648877 [00:07<00:40, 34120.28it/s]\u001b[A\n",
" 16% 262144/1648877 [00:07<00:40, 34152.33it/s]\u001b[A\n",
" 16% 270336/1648877 [00:08<00:40, 34154.08it/s]\u001b[A\n",
" 17% 278528/1648877 [00:08<00:40, 33446.95it/s]\u001b[A\n",
" 17% 286720/1648877 [00:08<00:41, 32998.52it/s]\u001b[A\n",
" 18% 294912/1648877 [00:08<00:41, 32659.12it/s]\u001b[A\n",
" 18% 303104/1648877 [00:09<00:41, 32453.69it/s]\u001b[A\n",
" 19% 311296/1648877 [00:09<00:41, 32282.52it/s]\u001b[A\n",
" 19% 319488/1648877 [00:09<00:41, 32194.51it/s]\u001b[A\n",
" 20% 327680/1648877 [00:09<00:41, 32084.61it/s]\u001b[A\n",
" 20% 335872/1648877 [00:10<00:41, 31877.34it/s]\u001b[A\n",
" 21% 344064/1648877 [00:10<00:40, 32101.09it/s]\u001b[A\n",
" 21% 352256/1648877 [00:10<00:40, 32031.75it/s]\u001b[A\n",
" 22% 360448/1648877 [00:10<00:40, 32004.28it/s]\u001b[A\n",
" 22% 368640/1648877 [00:11<00:39, 32008.77it/s]\u001b[A\n",
" 23% 376832/1648877 [00:11<00:39, 31982.60it/s]\u001b[A\n",
" 23% 385024/1648877 [00:11<00:39, 31989.36it/s]\u001b[A\n",
" 24% 393216/1648877 [00:11<00:39, 31933.49it/s]\u001b[A\n",
" 24% 401408/1648877 [00:12<00:39, 31984.12it/s]\u001b[A\n",
" 25% 409600/1648877 [00:12<00:38, 31968.13it/s]\u001b[A\n",
" 25% 417792/1648877 [00:12<00:38, 31957.29it/s]\u001b[A\n",
" 26% 425984/1648877 [00:12<00:38, 31896.58it/s]\u001b[A\n",
"9920512it [05:20, 33995.51it/s]\n",
" 27% 442368/1648877 [00:13<00:37, 31974.02it/s]\u001b[A\n",
" 27% 450560/1648877 [00:13<00:37, 32029.01it/s]\u001b[A\n",
" 28% 458752/1648877 [00:13<00:37, 31971.40it/s]\u001b[A\n",
" 28% 466944/1648877 [00:14<00:36, 31995.74it/s]\u001b[A\n",
" 29% 475136/1648877 [00:14<00:36, 31937.75it/s]\u001b[A\n",
" 29% 483328/1648877 [00:14<00:36, 31987.75it/s]\u001b[A\n",
" 30% 491520/1648877 [00:14<00:36, 31971.89it/s]\u001b[A\n",
" 30% 499712/1648877 [00:15<00:35, 31952.60it/s]\u001b[A\n",
" 31% 507904/1648877 [00:15<00:35, 31869.06it/s]\u001b[A\n",
" 31% 516096/1648877 [00:15<00:35, 31983.51it/s]\u001b[A\n",
" 32% 524288/1648877 [00:15<00:35, 31976.20it/s]\u001b[A\n",
" 32% 532480/1648877 [00:16<00:34, 31974.52it/s]\u001b[A\n",
" 33% 540672/1648877 [00:16<00:34, 31938.19it/s]\u001b[A\n",
" 33% 548864/1648877 [00:16<00:34, 31920.36it/s]\u001b[A\n",
" 34% 557056/1648877 [00:17<00:34, 31967.11it/s]\u001b[A\n",
" 34% 565248/1648877 [00:17<00:33, 31947.44it/s]\u001b[A\n",
" 35% 573440/1648877 [00:17<00:33, 31961.52it/s]\u001b[A\n",
" 35% 581632/1648877 [00:17<00:33, 31800.41it/s]\u001b[A\n",
" 36% 589824/1648877 [00:18<00:33, 31995.95it/s]\u001b[A\n",
" 36% 598016/1648877 [00:18<00:32, 31980.23it/s]\u001b[A\n",
" 37% 606208/1648877 [00:18<00:32, 31970.62it/s]\u001b[A\n",
" 37% 614400/1648877 [00:18<00:32, 31751.50it/s]\u001b[A\n",
" 38% 622592/1648877 [00:19<00:32, 31867.72it/s]\u001b[A\n",
" 38% 630784/1648877 [00:19<00:31, 32055.02it/s]\u001b[A\n",
" 39% 638976/1648877 [00:19<00:31, 32018.24it/s]\u001b[A\n",
" 39% 647168/1648877 [00:19<00:31, 31883.78it/s]\u001b[A\n",
" 40% 655360/1648877 [00:20<00:31, 32021.15it/s]\u001b[A\n",
" 40% 663552/1648877 [00:20<00:30, 31989.55it/s]\u001b[A\n",
" 41% 671744/1648877 [00:20<00:31, 31236.69it/s]\u001b[A\n",
" 41% 679936/1648877 [00:20<00:30, 32186.38it/s]\u001b[A\n",
" 42% 688128/1648877 [00:21<00:29, 32120.81it/s]\u001b[A\n",
" 42% 696320/1648877 [00:21<00:29, 32032.21it/s]\u001b[A\n",
" 43% 704512/1648877 [00:21<00:29, 32034.95it/s]\u001b[A\n",
" 43% 712704/1648877 [00:21<00:29, 31851.44it/s]\u001b[A\n",
" 44% 720896/1648877 [00:22<00:29, 31914.15it/s]\u001b[A\n",
" 44% 729088/1648877 [00:22<00:28, 31822.87it/s]\u001b[A\n",
" 45% 737280/1648877 [00:22<00:28, 32080.24it/s]\u001b[A\n",
" 45% 745472/1648877 [00:22<00:28, 31967.19it/s]\u001b[A\n",
" 46% 753664/1648877 [00:23<00:27, 32003.93it/s]\u001b[A\n",
" 46% 761856/1648877 [00:23<00:27, 32622.54it/s]\u001b[A\n",
" 47% 770048/1648877 [00:23<00:26, 33009.04it/s]\u001b[A\n",
" 47% 778240/1648877 [00:23<00:26, 33237.67it/s]\u001b[A\n",
" 48% 786432/1648877 [00:24<00:25, 33632.54it/s]\u001b[A\n",
" 48% 794624/1648877 [00:24<00:25, 33723.40it/s]\u001b[A\n",
" 49% 802816/1648877 [00:24<00:25, 33797.33it/s]\u001b[A\n",
" 49% 811008/1648877 [00:24<00:24, 33981.21it/s]\u001b[A\n",
" 50% 819200/1648877 [00:25<00:24, 33971.27it/s]\u001b[A\n",
" 50% 827392/1648877 [00:25<00:24, 33274.42it/s]\u001b[A\n",
" 51% 835584/1648877 [00:25<00:24, 32928.69it/s]\u001b[A\n",
" 51% 843776/1648877 [00:25<00:24, 32602.80it/s]\u001b[A\n",
" 52% 851968/1648877 [00:26<00:24, 32000.80it/s]\u001b[A\n",
" 52% 860160/1648877 [00:26<00:24, 32433.17it/s]\u001b[A\n",
" 53% 868352/1648877 [00:26<00:24, 32289.10it/s]\u001b[A\n",
" 53% 876544/1648877 [00:26<00:23, 32697.38it/s]\u001b[A\n",
" 54% 884736/1648877 [00:27<00:23, 33217.44it/s]\u001b[A\n",
" 54% 892928/1648877 [00:27<00:22, 33391.43it/s]\u001b[A\n",
" 55% 901120/1648877 [00:27<00:22, 33568.89it/s]\u001b[A\n",
" 55% 909312/1648877 [00:27<00:21, 33824.95it/s]\u001b[A\n",
" 56% 917504/1648877 [00:28<00:21, 33900.79it/s]\u001b[A\n",
" 56% 925696/1648877 [00:28<00:21, 33794.63it/s]\u001b[A\n",
" 57% 933888/1648877 [00:28<00:21, 34035.17it/s]\u001b[A\n",
" 57% 942080/1648877 [00:28<00:21, 33380.91it/s]\u001b[A\n",
" 58% 950272/1648877 [00:29<00:21, 32924.76it/s]\u001b[A\n",
" 58% 958464/1648877 [00:29<00:21, 32637.90it/s]\u001b[A\n",
" 59% 966656/1648877 [00:29<00:21, 32394.94it/s]\u001b[A\n",
" 59% 974848/1648877 [00:29<00:20, 32257.29it/s]\u001b[A\n",
" 60% 983040/1648877 [00:30<00:20, 32163.34it/s]\u001b[A\n",
" 60% 991232/1648877 [00:30<00:20, 32119.69it/s]\u001b[A\n",
" 61% 999424/1648877 [00:30<00:20, 32062.27it/s]\u001b[A\n",
" 61% 1007616/1648877 [00:30<00:20, 32028.97it/s]\u001b[A\n",
" 62% 1015808/1648877 [00:31<00:19, 32014.44it/s]\u001b[A\n",
" 62% 1024000/1648877 [00:31<00:19, 31957.17it/s]\u001b[A\n",
" 63% 1032192/1648877 [00:31<00:19, 31986.16it/s]\u001b[A\n",
" 63% 1040384/1648877 [00:31<00:19, 31927.45it/s]\u001b[A\n",
" 64% 1048576/1648877 [00:32<00:18, 31970.84it/s]\u001b[A\n",
" 64% 1056768/1648877 [00:32<00:18, 31892.02it/s]\u001b[A\n",
" 65% 1064960/1648877 [00:32<00:18, 31988.95it/s]\u001b[A\n",
" 65% 1073152/1648877 [00:32<00:18, 31879.86it/s]\u001b[A\n",
" 66% 1081344/1648877 [00:33<00:17, 31994.49it/s]\u001b[A\n",
" 66% 1089536/1648877 [00:33<00:17, 31957.58it/s]\u001b[A\n",
" 67% 1097728/1648877 [00:33<00:17, 31986.09it/s]\u001b[A\n",
" 67% 1105920/1648877 [00:33<00:16, 31976.83it/s]\u001b[A\n",
" 68% 1114112/1648877 [00:34<00:16, 31971.22it/s]\u001b[A\n",
" 68% 1122304/1648877 [00:34<00:16, 31935.26it/s]\u001b[A\n",
" 69% 1130496/1648877 [00:34<00:16, 31946.34it/s]\u001b[A\n",
" 69% 1138688/1648877 [00:34<00:16, 31777.00it/s]\u001b[A\n",
" 70% 1146880/1648877 [00:35<00:15, 31417.72it/s]\u001b[A\n",
" 70% 1155072/1648877 [00:35<00:15, 31499.40it/s]\u001b[A\n",
" 71% 1163264/1648877 [00:35<00:15, 32311.64it/s]\u001b[A\n",
" 71% 1171456/1648877 [00:35<00:14, 32191.01it/s]\u001b[A\n",
" 72% 1179648/1648877 [00:36<00:14, 32105.31it/s]\u001b[A\n",
" 72% 1187840/1648877 [00:36<00:14, 31991.41it/s]\u001b[A\n",
" 73% 1196032/1648877 [00:36<00:14, 32067.65it/s]\u001b[A\n",
" 73% 1204224/1648877 [00:37<00:13, 31954.60it/s]\u001b[A\n",
" 74% 1212416/1648877 [00:37<00:13, 32030.41it/s]\u001b[A\n",
" 74% 1220608/1648877 [00:37<00:13, 31972.29it/s]\u001b[A\n",
" 75% 1228800/1648877 [00:37<00:13, 31964.06it/s]\u001b[A\n",
" 75% 1236992/1648877 [00:38<00:12, 31992.65it/s]\u001b[A\n",
" 76% 1245184/1648877 [00:38<00:12, 31868.23it/s]\u001b[A\n",
" 76% 1253376/1648877 [00:38<00:12, 31970.22it/s]\u001b[A\n",
" 77% 1261568/1648877 [00:38<00:12, 31967.06it/s]\u001b[A\n",
" 77% 1269760/1648877 [00:39<00:11, 31967.24it/s]\u001b[A\n",
" 78% 1277952/1648877 [00:39<00:11, 31975.81it/s]\u001b[A\n",
" 78% 1286144/1648877 [00:39<00:11, 31972.34it/s]\u001b[A\n",
" 78% 1294336/1648877 [00:39<00:11, 31869.73it/s]\u001b[A\n",
" 79% 1302528/1648877 [00:40<00:10, 31901.65it/s]\u001b[A\n",
" 79% 1310720/1648877 [00:40<00:10, 31875.45it/s]\u001b[A\n",
" 80% 1318912/1648877 [00:40<00:10, 32001.27it/s]\u001b[A\n",
" 80% 1327104/1648877 [00:40<00:10, 31989.57it/s]\u001b[A\n",
" 81% 1335296/1648877 [00:41<00:09, 31979.08it/s]\u001b[A\n",
" 81% 1343488/1648877 [00:41<00:09, 31976.62it/s]\u001b[A\n",
" 82% 1351680/1648877 [00:41<00:09, 31949.45it/s]\u001b[A\n",
" 82% 1359872/1648877 [00:41<00:09, 31956.15it/s]\u001b[A\n",
" 83% 1368064/1648877 [00:42<00:08, 31970.05it/s]\u001b[A\n",
" 83% 1376256/1648877 [00:42<00:08, 31905.09it/s]\u001b[A\n",
" 84% 1384448/1648877 [00:42<00:08, 31975.66it/s]\u001b[A\n",
" 84% 1392640/1648877 [00:42<00:08, 31957.88it/s]\u001b[A\n",
" 85% 1400832/1648877 [00:43<00:07, 31954.25it/s]\u001b[A\n",
" 85% 1409024/1648877 [00:43<00:07, 31824.22it/s]\u001b[A\n",
" 86% 1417216/1648877 [00:43<00:07, 31989.36it/s]\u001b[A\n",
" 86% 1425408/1648877 [00:43<00:07, 31834.71it/s]\u001b[A\n",
" 87% 1433600/1648877 [00:44<00:06, 32013.62it/s]\u001b[A\n",
" 87% 1441792/1648877 [00:44<00:06, 31994.63it/s]\u001b[A\n",
" 88% 1449984/1648877 [00:44<00:06, 31978.23it/s]\u001b[A\n",
" 88% 1458176/1648877 [00:44<00:05, 31785.65it/s]\u001b[A\n",
" 89% 1466368/1648877 [00:45<00:05, 31987.42it/s]\u001b[A\n",
" 89% 1474560/1648877 [00:45<00:05, 31907.18it/s]\u001b[A\n",
" 90% 1482752/1648877 [00:45<00:05, 32017.74it/s]\u001b[A\n",
" 90% 1490944/1648877 [00:45<00:04, 31919.24it/s]\u001b[A\n",
" 91% 1499136/1648877 [00:46<00:04, 31920.86it/s]\u001b[A\n",
" 91% 1507328/1648877 [00:46<00:04, 32006.41it/s]\u001b[A\n",
" 92% 1515520/1648877 [00:46<00:04, 31823.83it/s]\u001b[A\n",
" 92% 1523712/1648877 [00:46<00:03, 33251.87it/s]\u001b[A\n",
" 93% 1531904/1648877 [00:47<00:03, 32877.87it/s]\u001b[A\n",
" 93% 1540096/1648877 [00:47<00:03, 32550.60it/s]\u001b[A\n",
" 94% 1548288/1648877 [00:47<00:03, 32387.69it/s]\u001b[A\n",
" 94% 1556480/1648877 [00:47<00:02, 32767.84it/s]\u001b[A\n",
" 95% 1564672/1648877 [00:48<00:02, 33278.77it/s]\u001b[A\n",
" 95% 1572864/1648877 [00:48<00:02, 33517.76it/s]\u001b[A\n",
" 96% 1581056/1648877 [00:48<00:02, 33653.92it/s]\u001b[A\n",
" 96% 1589248/1648877 [00:48<00:01, 33785.58it/s]\u001b[A\n",
" 97% 1597440/1648877 [00:49<00:01, 33865.54it/s]\u001b[A\n",
" 97% 1605632/1648877 [00:49<00:01, 33953.46it/s]\u001b[A\n",
" 98% 1613824/1648877 [00:49<00:01, 33945.79it/s]\u001b[A\n",
" 98% 1622016/1648877 [00:49<00:00, 34031.29it/s]\u001b[A\n",
" 99% 1630208/1648877 [00:50<00:00, 33968.15it/s]\u001b[A\n",
" 99% 1638400/1648877 [00:50<00:00, 33401.37it/s]\u001b[A\n",
"100% 1646592/1648877 [00:50<00:00, 32929.03it/s]\u001b[A\n",
"1654784it [00:50, 29986.01it/s] \u001b[AExtracting /tmp/mnist/data/MNIST/raw/t10k-images-idx3-ubyte.gz to /tmp/mnist/data/MNIST/raw\n",
"Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz to /tmp/mnist/data/MNIST/raw/t10k-labels-idx1-ubyte.gz\n",
"\n",
"\n",
"0it [00:00, ?it/s]\u001b[A\u001b[A\n",
"\n",
"8192it [00:00, 18417.06it/s]\n",
"Extracting /tmp/mnist/data/MNIST/raw/t10k-labels-idx1-ubyte.gz to /tmp/mnist/data/MNIST/raw\n",
"Processing...\n",
"/pytorch/torch/csrc/utils/tensor_numpy.cpp:141: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program.\n",
"Done!\n",
"Train Epoch: 1 [0/60000 (0%)]\tLoss: 2.338660\n",
"Train Epoch: 1 [6400/60000 (11%)]\tLoss: 0.845277\n",
"\n",
"1654784it [01:03, 29986.01it/s]\u001b[ATrain Epoch: 1 [12800/60000 (21%)]\tLoss: 0.509347\n",
"Train Epoch: 1 [19200/60000 (32%)]\tLoss: 0.086940\n",
"Train Epoch: 1 [25600/60000 (43%)]\tLoss: 0.230161\n",
"Train Epoch: 1 [32000/60000 (53%)]\tLoss: 0.118194\n",
"Train Epoch: 1 [38400/60000 (64%)]\tLoss: 0.115939\n",
"Train Epoch: 1 [44800/60000 (75%)]\tLoss: 0.084920\n",
"Train Epoch: 1 [51200/60000 (85%)]\tLoss: 0.065683\n",
"Train Epoch: 1 [57600/60000 (96%)]\tLoss: 0.050990\n",
"\n",
"Test set: Average loss: 0.0827, Accuracy: 9752/10000 (98%)\n",
"\n",
"Train Epoch: 2 [0/60000 (0%)]\tLoss: 0.104688\n",
"Train Epoch: 2 [6400/60000 (11%)]\tLoss: 0.124440\n",
"Train Epoch: 2 [12800/60000 (21%)]\tLoss: 0.065664\n",
"Train Epoch: 2 [19200/60000 (32%)]\tLoss: 0.105990\n",
"Train Epoch: 2 [25600/60000 (43%)]\tLoss: 0.298882\n",
"Train Epoch: 2 [32000/60000 (53%)]\tLoss: 0.046234\n",
"Train Epoch: 2 [38400/60000 (64%)]\tLoss: 0.053398\n",
"Train Epoch: 2 [44800/60000 (75%)]\tLoss: 0.148264\n",
"Train Epoch: 2 [51200/60000 (85%)]\tLoss: 0.048250\n",
"Train Epoch: 2 [57600/60000 (96%)]\tLoss: 0.138816\n",
"\n",
"Test set: Average loss: 0.0533, Accuracy: 9818/10000 (98%)\n",
"\n",
"[TensorRT] WARNING: TensorRT was linked against cuDNN 8.0.5 but loaded cuDNN 8.0.4\n",
"[TensorRT] WARNING: TensorRT was linked against cuDNN 8.0.5 but loaded cuDNN 8.0.4\n",
"[TensorRT] WARNING: TensorRT was linked against cuDNN 8.0.5 but loaded cuDNN 8.0.4\n",
"Test Case: 1\n",
"Prediction: 1\n",
"\n",
"9920512it [08:36, 19192.45it/s]\n",
"1654784it [03:30, 7876.48it/s]\n"
],
"name": "stdout"
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment